Writer Recognition Using Off-line Handwritten Single Block Characters

TL;DR

This study demonstrates that individual handwritten digits, specifically date of birth, contain biometric information that can be used for writer recognition, achieving high accuracy with deep learning methods on a small dataset.

Contribution

It introduces a novel approach to writer recognition using off-line handwritten digits, comparing handcrafted and deep features, and evaluates performance with limited enrollment samples.

Findings

Deep features achieve 94% Top-1 accuracy with ten enrollment samples.

Biometric information is present in just six handwritten digits.

Recognition performance improves with more enrollment samples.

Abstract

Block characters are often used when filling paper forms for a variety of purposes. We investigate if there is biometric information contained within individual digits of handwritten text. In particular, we use personal identity numbers consisting of the six digits of the date of birth, DoB. We evaluate two recognition approaches, one based on handcrafted features that compute contour directional measurements, and another based on deep features from a ResNet50 model. We use a self-captured database of 317 individuals and 4920 written DoBs in total. Results show the presence of identity-related information in a piece of handwritten information as small as six digits with the DoB. We also analyze the impact of the amount of enrolment samples, varying its number between one and ten. Results with such small amount of data are promising. With ten enrolment samples, the Top-1 accuracy with deep features is around 94%, and reaches nearly 100% by Top-10. The verification accuracy is more modest, with EER>20%with any given feature and enrolment set size, showing that there is still room for improvement.